Large language models (LLMs) show strong general capability but often struggle with medical terminology precision and safety-critical instruction following. We present a case study for adapter interference in safety-critical domains using a 14B-parameter base model through a two-stage LoRA pipeline: (1) domain-adaptive pre-training (PT) to inject broad medical knowledge via continued pre-training (DAPT), and (2) supervised fine-tuning (SFT) to align the model with medical question-answering behaviors through instruction-style data. To balance instruction-following ability and domain knowledge retention, we propose Weighted Adapter Merging, linearly combining SFT and PT adapters before exporting a merged base-model checkpoint. On a held-out medical validation set (F5/F6), the merged model achieves BLEU-4 = 16.38, ROUGE-1 = 20.42, ROUGE-2 = 4.60, and ROUGE-L = 11.54 under a practical decoding configuration. We further analyze decoding sensitivity and training stability with loss curves and controlled decoding comparisons.

翻译：大语言模型展现出强大的通用能力，但在医学术语精确性和安全关键指令遵循方面常显不足。我们通过一个两阶段LoRA流程，基于一个140亿参数的基础模型，对安全关键领域中的适配器干扰现象进行了案例研究：(1) 领域自适应预训练通过持续预训练注入广泛的医学知识；(2) 监督微调通过指令式数据使模型与医学问答行为对齐。为平衡指令遵循能力和领域知识保留，我们提出加权适配器合并方法，在导出合并后的基础模型检查点之前，对SFT和PT适配器进行线性组合。在保留的医学验证集上，合并模型在实用解码配置下取得了BLEU-4 = 16.38、ROUGE-1 = 20.42、ROUGE-2 = 4.60和ROUGE-L = 11.54的成绩。我们进一步通过损失曲线和受控解码对比分析了解码敏感性和训练稳定性。